Answer patient enquiries for a clinic by chat
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.
A user had Claude Cowork read 400 PDF files and sort them into different folders.
A user had Claude Cowork read 400 PDF files and sort them into different folders.
The user put all the PDFs in one local folder, selected that folder in Claude Cowork, and gave a plain-language instruction saying how many files were there, what text to look for, and which matching files should be moved into one or more subfolders. They said Cowork handled text-based PDFs, could also group related PDFs for merging, and after sorting they could ask it to generate an XLSX index showing what went where.
They reported Cowork sorted 400 PDFs without trouble; in the more detailed follow-up they described the same workflow on 382 files. The source gives no measured accuracy, speed, or examples of mistakes, only that it worked for text rather than image content.
Their main tip was to be very explicit in the prompt, like briefing a smart new coworker; they only made a reusable skill if it was something they wanted to repeat.
Read the PDFs in [folder path] and sort them into subfolders by [criteria, e.g. client, document type, or year]. First show me the proposed folder names and a sample of how files would be assigned, and wait for my OK. Then move the files, never delete anything, and finish with a list of any files you couldn't classify.
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.
An n8n workflow has AI classify web-form jobs by type, urgency and summary, create an Airtable record, reply instantly and flag uncertain cases.
Lindy agents summarized meeting notes, sent action items to teammates, suggested knowledge-base replies on support tickets, and handled follow-up emails and calendar updates.